Microsoft Technology Licensing, LLC

Xiaoyi Zhang

Meredith June Morris

Harish Kulkarni

Qi Guo

Daniel Sairom Krishnan Hewlett

Dan Liu

Xuebin Yan

Wenxiang Chen

Lester Gilbert Cottle, Iii

Yu Gong

Haitong Tian

Siyao Sun

Pei-Lun Liao

In an example embodiment, position bias and other types of bias may be compensated for by using two-phase training of a machine-learned model. In a first phase, the machine-learned model is trained using non-randomized training data. Since certain types of machine-learned models, such as those involving deep learning (e.g., neural networks) require a lot of training data, this allows the bulk of the training to be devoted to training using non-randomized training data. However, since this non-randomized training data may be biased, a second training phase is then used to revise the machine-learned model based on randomized training data to remove the bias from the machine-learned model. Since this randomized training data may be less plentiful, this allows the deep learning machine-learned model to be trained to operate in an unbiased manner without the need to generate additional randomized training data.

Two-stage training with non-randomized and randomized data

Techniques for text entry using gestures are disclosed. As disclosed, a camera may capture a frame and the face of the user can be detected therein. Landmarks can be aligned to the face in the captured frame. A left eye image and a right eye image may be extracted from the captured frame. The left eye image and the right image each may be resized and compared to a calibration template. A direction of eye gaze may be determined based upon the comparison. A character or word may be predicted based upon the determination of the direction of eye gaze and a known configuration of an eye gaze board (e.g., an E-tran board). The predicted character or word can be included as a part of a text-based message.

Automated E-tran application

Growing community of inventors

Sunnyvale, CA, United States of America

Xiaoyi Zhang